The Robust Malware Detection Challenge and Greedy Random Accelerated Multi-Bit Search

S.E. Verwer, A. Nadeem, C.A. Hammerschmidt, L. Bliek, Abdullah Al-Dujaili, Una-May O’Reilly

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

8 Citations (Scopus)
193 Downloads (Pure)


Training classifiers that are robust against adversarially modified examples is becoming increasingly important in practice. In the field of malware detection, adversaries modify malicious binary files to seem benign while preserving their malicious behavior. We report on the results of a recently held robust malware detection challenge. There were two tracks in which teams could participate: the attack track asked for adversarially modified malware samples and the defend track asked for trained neural network classifiers that are robust to such modifications. The teams were unaware of the attacks/defenses they had to detect/evade. Although only 9 teams participated, this unique setting allowed us to make several interesting observations. We also present the challenge winner: GRAMS, a family of novel techniques to train adversarially robust networks that preserve the intended (malicious) functionality and yield high-quality adversarial samples. These samples are used to iteratively train a robust classifier. We show that our techniques, based on discrete optimization techniques, beat purely gradient-based methods. GRAMS obtained first place in both the attack and defend tracks of the competition.
Original languageEnglish
Title of host publicationWorkshop on artificial intelligence and security
Place of PublicationNew York
PublisherAssociation for Computing Machinery (ACM)
Number of pages10
ISBN (Electronic)978-1-4503-8094-2
Publication statusPublished - 2020
Event13th ACM Workshop on
Artificial Intelligence and Security
- Orlando, United States
Duration: 13 Nov 202013 Nov 2020
Conference number: 13


Conference13th ACM Workshop on
Artificial Intelligence and Security
Abbreviated titleAISec 2020
Country/TerritoryUnited States

Bibliographical note

Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project

Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.


  • Adversarial Learning
  • Neural Networks
  • Robust Malware Detection
  • Adversarial malware
  • Discrete optimization
  • Saddle-point optimization


Dive into the research topics of 'The Robust Malware Detection Challenge and Greedy Random Accelerated Multi-Bit Search'. Together they form a unique fingerprint.

Cite this